Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12601
    Prev
    Next
    INDEX
    Explanations

    references to utility functions or modules in programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.82
     Gorbachev
    -0.82
     CreateTagHelper
    -0.81
     GenerationType
    -0.79
     doInBackground
    -0.79
    modelBuilder
    -0.78
    psum
    -0.75
    RunWith
    -0.73
    GEBURTS
    -0.73
     Brecht
    -0.73
    POSITIVE LOGITS
    Util
    1.37
     Util
    1.30
    Utils
    1.25
     util
    1.24
     utils
    1.24
    util
    1.16
     Utils
    1.15
     utility
    1.09
    工具类
    1.06
    utils
    1.03
    Activations Density 0.074%

    No Known Activations